Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: cc-by-nc-sa-4.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-sa-4.0
|
| 3 |
+
---
|
| 4 |
+
# Dalla (دلّة) - Arabic Language Models
|
| 5 |
+
|
| 6 |
+
Dalla is a family of Arabic language models optimized for Arabic text processing through advanced tokenization techniques.
|
| 7 |
+
|
| 8 |
+
## Available Models
|
| 9 |
+
|
| 10 |
+
### Instruction-Tuned Variants
|
| 11 |
+
|
| 12 |
+
- **[Dalla-Gemma-IT](https://huggingface.co/U4RASD/dalla-gemma-it)** - Instruction-tuned variant based on Gemma architecture
|
| 13 |
+
- **[Dalla-Llama-IT](https://huggingface.co/U4RASD/dalla-llama-it)** - Instruction-tuned variant based on Llama architecture
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
```python
|
| 19 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 20 |
+
|
| 21 |
+
# Load model and tokenizer
|
| 22 |
+
model_name = "U4RASD/dalla-gemma-it" # or "U4RASD/dalla-llama-it"
|
| 23 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 24 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|